Semi-Supervised Learning with Multi-Head Co-Training
This work addresses the problem of making co-training more efficient and practical for semi-supervised learning, though it appears incremental as it builds on existing co-training frameworks.
The paper tackles the challenge of single-view co-training in semi-supervised learning by introducing Multi-Head Co-Training, which uses a multi-head structure and a 'Weak and Strong Augmentation' strategy to promote diversity with minimal extra parameters, resulting in demonstrated effectiveness on standard benchmarks.
Co-training, extended from self-training, is one of the frameworks for semi-supervised learning. Without natural split of features, single-view co-training works at the cost of training extra classifiers, where the algorithm should be delicately designed to prevent individual classifiers from collapsing into each other. To remove these obstacles which deter the adoption of single-view co-training, we present a simple and efficient algorithm Multi-Head Co-Training. By integrating base learners into a multi-head structure, the model is in a minimal amount of extra parameters. Every classification head in the unified model interacts with its peers through a "Weak and Strong Augmentation" strategy, in which the diversity is naturally brought by the strong data augmentation. Therefore, the proposed method facilitates single-view co-training by 1). promoting diversity implicitly and 2). only requiring a small extra computational overhead. The effectiveness of Multi-Head Co-Training is demonstrated in an empirical study on standard semi-supervised learning benchmarks.